arXiv:2509.25606v3 Announce Type: replace Abstract: This article initiates the study of a basic question about model pruning. Given a vector $s$ of importance scores assigned to model components, how many of the scored components could be discarded without sacrificing performance?…
arXiv:2605.20272v1 Announce Type: new Abstract: While humans readily generalize abstract concepts to more complex or larger tasks, building Reinforcement Learning (RL) systems with this ability remains elusive. Here, we present the first theoretical model of how such Out-of-Distribution (OOD) generalization…
arXiv:2602.08686v2 Announce Type: replace Abstract: Prefill-only KV compression freezes a token subset at the end of prefill and decodes from it without further eviction. The retention decision is therefore irreversible, yet existing methods estimate the corrective signals it relies on,…
arXiv:2605.20273v1 Announce Type: new Abstract: Online model editing for multimodal large language models (MLLMs) requires assimilating a stream of corrections under tight compute and memory budgets. Yet editors developed for text-only LLMs often degrade on MLLMs: visually dominant activations skew…
arXiv:2604.07213v2 Announce Type: replace Abstract: High-dimensional data are often assumed to lie on lower-dimensional manifolds. We study how to construct diffusion processes on this data manifold using only point cloud samples and without access to charts, projections, or other geometric…
arXiv:2605.20276v1 Announce Type: new Abstract: The global deployment of edge intelligence operates across heterogeneous legal frameworks. While some regions permit centralized learning (CL) via cloud data aggregation, others enforce strict data localization, necessitating federated learning (FL). This operational dichotomy introduces…
arXiv:2605.08123v2 Announce Type: replace Abstract: We study long-context balanced entropic optimal transport (OT) attention on TPU hardware through a stopped-base, fixed-depth tail-refinement surrogate. After a stopped $T$-step Sinkhorn solve, we unroll a short refinement tail and differentiate that surrogate exactly.…
arXiv:2605.20278v1 Announce Type: new Abstract: Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the level of individual visual claims. A good dense caption should be both…
arXiv:2605.18848v2 Announce Type: replace Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation error. We identify and address two…
arXiv:2605.12597v2 Announce Type: replace-cross Abstract: Computational sampling has been central to the sciences since the mid-20th century. While machine-learning-based approaches have recently enabled major advances, their behavior remains poorly understood, with limited theoretical control over when and why they succeed.…
